The high computation and memory storage of large deep neural networks (DNNs) models pose intensive challenges to the conventional Von-Neumann architecture, incurring substantial data movements in the memory hierarchy. The memristor crossbar array has emerged as a promising solution to mitigate the challenges and enable low-power acceleration of DNNs. Memristor-based weight pruning and weight quantization have been seperately investigated and proven effectiveness in reducing area and power consumption compared to the original DNN model. However, there has been no systematic investigation of memristor-based neuromorphic computing (NC) systems considering both weight pruning and weight quantization. In this paper, we propose an unified and systematic memristorbased framework considering both structured weight pruning and weight quantization by incorporating alternating direction method of multipliers (ADMM) into DNNs training. We consider hardware constraints such as crossbar blocks pruning, conductance range, and mismatch between weight value and real devices, to achieve high accuracy and low power and small area footprint. Our framework is mainly integrated by three steps, i.e., memristorbased ADMM regularized optimization, masked mapping and retraining. Experimental results show that our proposed framework achieves 29.81× (20.88×) weight compression ratio, with 98.38% (96.96%) and 98.29% (97.47%) power and area reduction on VGG-16 (ResNet-18) network where only have 0.5% (0.76%) accuracy loss, compared to the original DNN models. We share our models at anonymous link http://bit.ly/2Jp5LHJ.
Due to the large scales and limitations in accessing most online social networks, it is hard or infeasible to directly access them in a reasonable amount of time for studying and analysis. Hence, network sampling has emerged as a suitable technique to study and analyze real networks. The main goal of sampling online social networks is constructing a small scale sampled network which preserves the most important properties of the original network. In this paper, we propose two sampling algorithms for sampling online social networks using spanning trees. The first proposed sampling algorithm finds several spanning trees from randomly chosen starting nodes; then the edges in these spanning trees are ranked according to the number of times that each edge has appeared in the set of found spanning trees in the given network. The sampled network is then constructed as a sub-graph of the original network which contains a fraction of nodes that are incident on highly ranked edges. In order to avoid traversing the entire network, the second sampling algorithm is proposed using partial spanning trees. The second sampling algorithm is similar to the first algorithm except that it uses partial spanning trees. Several experiments are conducted to examine the performance of the proposed sampling algorithms on well-known real networks. The obtained results in comparison with other popular sampling methods demonstrate the efficiency of the proposed sampling algorithms in terms of Kolmogorov–Smirnov distance (KSD), skew divergence distance (SDD) and normalized distance (ND).
Social networks form a major parts of people’s lives, and individuals often make important life decisions based on information that spreads through these networks. For this reason, it is important to know whether individuals from different protected groups have equal access to information flowing through a network. In this paper, we define the Information Unfairness (IUF) metric, which quantifies inequality in access to information across protected groups. We then introduce MinIUF , an algorithm for reducing inequalities in information flow by adding edges to the network. Finally, we provide an in-depth analysis of information flow with respect to an attribute of interest, such as gender, across different types of networks to evaluate whether the structure of these networks allows groups to equally access information flowing in the network. Moreover, we investigate the causes of unfairness in such networks and how it can be improved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.